Abstract
AbstractThe input data to grammar learning algorithms often consist ofovert formsthat do not contain full structural descriptions. This lack of information may contribute to the failure of learning. Past work onOptimality TheoryintroducedRobust Interpretive Parsing(RIP) as a partial solution to this problem. We generalize RIP and suggest replacing the winner candidate with a weighted mean violation of the potential winner candidates. A Boltzmann distribution is introduced on the winner set, and the distribution’s parameter$$T$$is gradually decreased. Finally, we show that GRIP, theGeneralized Robust Interpretive Parsing Algorithmsignificantly improves the learning success rate in a model with standard constraints for metrical stress assignment.
Highlights
Computational learning algorithms in linguistics build up the learner’s grammar based on observed data
How should the learner pick a winner candidate? The solution proposed by Tesar and Smolensky (1998:251f), called Robust Interpretive Parsing (RIP) and inspired by the convergence of Expectation-Maximization algorithms, is to rely on the grammar Hl currently hypothesized by the learner
A second way of improving the learning algorithm concerns our remark on Eq (11): we argued that initially the learners have no reason for preferring any element of RipSet(o) over the other, and they should entertain a uniform distribution P over RipSet(o) in the first phase of the learning
Summary
Computational learning algorithms in linguistics build up the learner’s grammar based on observed data These data often contain, partial information only, hiding crucial details, which may mislead the learner. Learning methods often require the full structural description of the learning data (the surface forms), including crucial information, such as semantic relations, coindexation and parsing brackets. These do not appear in the overt forms, as uttered by the speaker-teacher. It terminates by illustrating the limitations of the traditional approach to the problem just outlined, Robust Interpretive Parsing (Tesar and Smolensky 1998, 2000).
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
